Automatically classify open-ended survey feedback
When a user completes a survey in InputKit, send the feedback text to LLM as a Service to automatically extract themes and classify respondent sentiments.
See all LLM as a Service + InputKit integrations or talk to a human
Opens Claude with Knit filled in: click Continue. Claude web and desktop share one connector list. Or paste this link in Settings > Connectors > Add custom connector.
curl -fsSL https://raw.githubusercontent.com/knitapi/knit-plugin/main/plugins/knit/skills/knit/scripts/install.sh | bash -s -- --agents claude
Run in your own terminal, then restart Claude Code. Adds the server, the Knit skill and a CLAUDE.md note.
Turn on developer mode, then create a connector named Knit with this link and No Auth.
curl -fsSL https://raw.githubusercontent.com/knitapi/knit-plugin/main/plugins/knit/skills/knit/scripts/install.sh | bash -s -- --agents codex
Run in your own terminal (not through Codex), then start a new Codex session.
curl -fsSL https://raw.githubusercontent.com/knitapi/knit-plugin/main/plugins/knit/skills/knit/scripts/install.sh | bash -s -- --agents antigravity
Run in your own terminal, then reload MCP servers (/mcp in the CLI, refresh in the IDE).
curl -fsSL https://raw.githubusercontent.com/knitapi/knit-plugin/main/plugins/knit/skills/knit/scripts/install.sh | bash -s -- --agents cursor
Run in your own terminal, restart Cursor, then paste the note it prints into User Rules.
Google for Startups AcceleratorHow Knit builds this workflow
The Agent researches both APIs and wires the trigger on one side to the action on the other — no pre-built connector required. Here is the vocabulary it has to work with.
LLM as a Service Explore LLM as a Service →
TriggersFires when LLM as a Service returns a completion, prediction or other result.
Fires when a request to LLM as a Service errors or times out.
Fires when a fine-tuning job in LLM as a Service finishes.
Sends a prompt to LLM as a Service and returns the model's response.
Sends text, an image or other data to LLM as a Service and returns the model's output.
Uses LLM as a Service to classify or extract structured data from text or images.
InputKit Explore InputKit →
TriggersFires when a form is submitted in InputKit.
Fires when a respondent finishes a survey in InputKit.
Fires when an existing response is edited in InputKit.
Creates or updates a form or survey in InputKit.
Looks up a specific form response in InputKit.
Adds a respondent or contact to a form in InputKit.
More LLM as a Service + InputKit workflows
See all LLM as a Service + InputKit integrations → · Browse the full workflow library →
Enterprise-grade security
Common questions
Can Knit build “Automatically classify open-ended survey feedback” between LLM as a Service and InputKit?
Yes — describe it in the box above and Knit's Integrations Agent researches LLM as a Service and InputKit's public API docs (or your own uploaded docs) and builds a working workflow, whether or not either app already has a pre-built connector.
How long does it take to build?
Minutes to a first working version, not weeks — you test it against real data before it goes anywhere near production.
How does LLM as a Service improve how we process survey data from InputKit?
When customers complete surveys in InputKit, LLM as a Service can instantly summarize long responses, extract key themes, or categorize customer feedback without manual reading.
Can generated AI insights in LLM as a Service be saved back into InputKit?
Yes, after LLM as a Service analyzes or summarizes response text, the resulting completion can be saved directly back into InputKit to enrich the response record.